An Impoved Image Registration Method Based on SIFT and SC-RANSAC Algorithm

In order to improve the speed and accuracy of image registration, this paper proposes a hybrid algorithm combined SIFT and SC-RANSAC algorithm. It utilizes the SIFT algorithm to extract the feature points, and then utilizes nearest-neighbor method to find the matching points of two images. Finally, the SC-RANSAC algorithm is used to get rid of the wrong matching points. The experimental result shows that the proposed algorithm runs faster than algorithm combining SIFT with RANSAC.